@inproceedings{okano-etal-2021-contrastive,
title = "Contrastive Response Pairs for Automatic Evaluation of Non-task-oriented Neural Conversational Models",
author = "Okano, Koshiro and
Suzuki, Yu and
Kawamura, Masaya and
Kato, Tsuneo and
Tamura, Akihiro and
Wu, Jianming",
editor = "Li, Haizhou and
Levow, Gina-Anne and
Yu, Zhou and
Gupta, Chitralekha and
Sisman, Berrak and
Cai, Siqi and
Vandyke, David and
Dethlefs, Nina and
Wu, Yan and
Li, Junyi Jessy",
booktitle = "Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = jul,
year = "2021",
address = "Singapore and Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigdial-1.21",
doi = "10.18653/v1/2021.sigdial-1.21",
pages = "202--207",
abstract = "Responses generated by neural conversational models (NCMs) for non-task-oriented systems are difficult to evaluate. We propose contrastive response pairs (CRPs) for automatically evaluating responses from non-task-oriented NCMs. We conducted an error analysis on responses generated by an encoder-decoder recurrent neural network (RNN) type NCM and created three types of CRPs corresponding to the three most frequent errors found in the analysis. Three NCMs of different response quality were objectively evaluated with the CRPs and compared to a subjective assessment. The correctness obtained by the three types of CRPs were consistent with the results of the subjective assessment.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="okano-etal-2021-contrastive">
<titleInfo>
<title>Contrastive Response Pairs for Automatic Evaluation of Non-task-oriented Neural Conversational Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Koshiro</namePart>
<namePart type="family">Okano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaya</namePart>
<namePart type="family">Kawamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsuneo</namePart>
<namePart type="family">Kato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akihiro</namePart>
<namePart type="family">Tamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianming</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haizhou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gina-Anne</namePart>
<namePart type="family">Levow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chitralekha</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berrak</namePart>
<namePart type="family">Sisman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vandyke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Dethlefs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore and Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Responses generated by neural conversational models (NCMs) for non-task-oriented systems are difficult to evaluate. We propose contrastive response pairs (CRPs) for automatically evaluating responses from non-task-oriented NCMs. We conducted an error analysis on responses generated by an encoder-decoder recurrent neural network (RNN) type NCM and created three types of CRPs corresponding to the three most frequent errors found in the analysis. Three NCMs of different response quality were objectively evaluated with the CRPs and compared to a subjective assessment. The correctness obtained by the three types of CRPs were consistent with the results of the subjective assessment.</abstract>
<identifier type="citekey">okano-etal-2021-contrastive</identifier>
<identifier type="doi">10.18653/v1/2021.sigdial-1.21</identifier>
<location>
<url>https://aclanthology.org/2021.sigdial-1.21</url>
</location>
<part>
<date>2021-07</date>
<extent unit="page">
<start>202</start>
<end>207</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contrastive Response Pairs for Automatic Evaluation of Non-task-oriented Neural Conversational Models
%A Okano, Koshiro
%A Suzuki, Yu
%A Kawamura, Masaya
%A Kato, Tsuneo
%A Tamura, Akihiro
%A Wu, Jianming
%Y Li, Haizhou
%Y Levow, Gina-Anne
%Y Yu, Zhou
%Y Gupta, Chitralekha
%Y Sisman, Berrak
%Y Cai, Siqi
%Y Vandyke, David
%Y Dethlefs, Nina
%Y Wu, Yan
%Y Li, Junyi Jessy
%S Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2021
%8 July
%I Association for Computational Linguistics
%C Singapore and Online
%F okano-etal-2021-contrastive
%X Responses generated by neural conversational models (NCMs) for non-task-oriented systems are difficult to evaluate. We propose contrastive response pairs (CRPs) for automatically evaluating responses from non-task-oriented NCMs. We conducted an error analysis on responses generated by an encoder-decoder recurrent neural network (RNN) type NCM and created three types of CRPs corresponding to the three most frequent errors found in the analysis. Three NCMs of different response quality were objectively evaluated with the CRPs and compared to a subjective assessment. The correctness obtained by the three types of CRPs were consistent with the results of the subjective assessment.
%R 10.18653/v1/2021.sigdial-1.21
%U https://aclanthology.org/2021.sigdial-1.21
%U https://doi.org/10.18653/v1/2021.sigdial-1.21
%P 202-207
Markdown (Informal)
[Contrastive Response Pairs for Automatic Evaluation of Non-task-oriented Neural Conversational Models](https://aclanthology.org/2021.sigdial-1.21) (Okano et al., SIGDIAL 2021)
ACL